# Devstral Small 2 vs LBS-27B (slim)

> Devstral Small 2 scores 61 (C) to LBS-27B's 55.8 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/devstral-small-2-vs-lbs-27b.md (~8,950 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-lbs-27b.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-lbs-27b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Devstral Small 2 scores 61 (C) on agent readiness against LBS-27B's 55.8 (C), and leads in 3 of 4 scored categories. LBS-27B leads on agent interface. Both do open-weight models you run yourself.

- Devstral Small 2: C 61, rank #60 of 160 open-weight models · https://www.anchorterminal.com/tools/devstral-small-2.min.md
- LBS-27B: C 55.8, rank #118 of 160 open-weight models · https://www.anchorterminal.com/tools/lbs-27b.min.md
- Devstral Small 2, good for Developers who want a dependable local coding agent on one consumer GPU or a 32 GB Mac Ahead on Reach, 90 against 60; Risk, 60 against 50.
- LBS-27B, good for Agents with about 96 GB of GPU memory that need to find click targets on dense professional screenshots, or read fine detail in large images, and can run a small crop loop and wait for independent results. Ahead on Agent interface, 70 against 65.

| Category | Devstral Small 2 | LBS-27B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 60 |
| Risk (20%) | 60 | 50 |
| Agent interface (10%) | 65 | 70 |
| Documentation and upkeep (10%) | 46 | 43 |

| Fact (where they differ) | Devstral Small 2 | LBS-27B |
| --- | --- | --- |
| Vendor | Mistral AI | inclusionAI (Ant Group) |
| Licence | Apache-2.0 | Apache-2.0 (the card's metadata and licence section; the LICENSE file sits in the GitHub repository inclusionAI/UI-Venus on its LBS branch, not in the Hugging Face repository) |
| Last release | 2026-07-15 | 2026-10-26 |

Why the edge:
- Reach, Devstral Small 2 +30: Devstral Small 2 90 (Memory 25, the smallest build at 4 bits from a runtime's own library is Ollama's devstral-small-2 at Q4_K_M, 15 GB, and 15 GB × 1.2 = 18 GB, within 24 GB.); LBS-27B 60 (Memory earns 10, since the only build is 54.73 GB of BF16, about 66 GB with a fifth added, which fits the reference machine but not 64 GB.)
- Risk, Devstral Small 2 +10: Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.); LBS-27B 50 (File safety earns 15, safetensors only but with the documented route running the publisher's scripts to serve it and to write its system prompt.)
- Agent interface, LBS-27B +5: Devstral Small 2 65 (Chat template 20, chat_template.jinja in the repository (11,362 characters), with the tokenizer's tekken file for mistral-common.); LBS-27B 70 (The chat template earns 20, Qwen's Jinja file in the repository.)